TensorRT

product
1 mentions 1 recordings first heard Feb 2026 last heard 24 Feb ±0 this month

NVIDIA runtime optimizer used for accelerating model inference

Trend

mentions per day · public audio 7d30d6M12M
No mentions in the last 30d.Widen the range to see when TensorRT was said.

Moments

newest first · ▶ plays the moment
Stefano ErmonThe Neuron: AI Explained · Diffusion for Text: Why Mercury Could Make LLMs 10x Faster · 15:17 · 24 Feb
…Things like VLLM, SGLang, TensorRT, like there is pretty mature serving stacks for ultra-aggressive models.…
· Open transcript →
All 1 moments